Application of machine learning models to predict ecotoxicity of ionic liquids (Vibrio fischeri) using VolSurf principal properties

Abstract. Owing to the rapid growth in IL synthesis due feasible cation–anion combinations, knowledge of their toxicity is pertinent for successful application. Toxicity information measurement various ILs on a broad spectrum conditions through experimental techniques way demanding time, resources, and at times impractical. Various research works have been performed Quantitative Structure Activity/Property Relationship (QSAR/QSPR) prediction. In this study, ML models trained tested Vibrio fischeri data set using silico principal properties (PPs) as descriptors. Deploying aid considering both effect cations anions Among trained, Random Forest model proved be most precise nevertheless, decision tree was accurate consistent. Considering importance descriptors selection optimization.